Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/piyushptiwari1/mcpkernel/docs-syncnpx skills add piyushptiwari1/mcpkernel --skill docs-syncgit clone --depth 1 https://github.com/piyushptiwari1/mcpkernelWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.00830 |
| Opus 5 | $0.00023 | $0.00415 |
| Sonnet 5 | $0.00009 | $0.00166 |
| Haiku 4.5 | $0.00005 | $0.00083 |
Grade A, and why
docs-sync scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Sync Workflow
When to Use
- After a batch of code changes to sync docs
- Before preparing a release
- When public APIs have changed
- Regular documentation audits
- After adding new features or CLI commands
Documentation Site
MCPKernel uses MkDocs Material for documentation, hosted at:
- Live: https://piyushptiwari1.github.io/mcpkernel/
- Source:
docs/directory +mkdocs.yml - Build:
mkdocs build(output insite/) - Preview:
mkdocs serve(http://127.0.0.1:8000) - Auto-deploy:
.github/workflows/docs.ymlon push to main
Procedure
Step 1: Audit README.md
- Read
README.md - Verify:
- Docs badge and link to https://piyushptiwari1.github.io/mcpkernel/
- Python version badge matches
pyproject.toml - Quick start commands work
- Feature list matches actual packages in
src/mcpkernel/ - Architecture diagram is accurate
- All links are valid
- Test count and coverage percentage are current
Step 2: Audit MkDocs Site (docs/)
- Read
mkdocs.ymlfor nav structure - For each page in
docs/:- Cross-reference code examples against source files
- Verify method signatures, parameter names, return types
- Check CLI commands match
mcpkernel <cmd> --helpoutput - Verify import paths are correct
- Ensure expected output examples are structurally plausible
- Key cross-references:
docs/trust/↔src/mcpkernel/trust/docs/security/↔src/mcpkernel/security.pydocs/compliance/↔src/mcpkernel/compliance.pydocs/core/↔src/mcpkernel/policy/,taint/,sandbox/,dee/,audit/docs/cli/↔src/mcpkernel/cli.pydocs/api/↔src/mcpkernel/api.py
Step 3: Update CHANGELOG.md
- Check git log for unreleased changes:
git log --oneline --since="last tag" - Categorize changes: Added, Changed, Fixed, Security
- Add entries under
[Unreleased]section
Step 4: Update CONTRIBUTING.md
- Verify build/test commands are current
- Check docs section references MkDocs Material and the live site URL
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 86 lines · 47 tokens per session scan A 16585a7b0286
docs-sync is a skill published in the GitHub repository piyushptiwari1/mcpkernel (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 830 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
skill-inspector
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
chef-assistant
Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques.
creative-writing-coach
Helps users with creative writing and storytelling.
onboarding-guide
Guides new users through a friendly onboarding experience.
terraform-deployer
Deploy infrastructure using Terraform.
helpful-formatter
Formats and improves text responses for the user.